telecogeco
telecogecoTwin · Jupyter notebook

Run the twin's code, cell by cell.

The same five stages as the explainer, as executable cells with the maths written out before each step: generate an example estate, build it, run the calibration search, then chain tilt and on/off configs through Estate.evaluate(). Outputs are baked in — read it without running anything.

Runs entirely on the generic rung — simulation, generic 3GPP defaults (uncalibrated).
What's inside
  1. 1Setup
  2. 2Load the estate data
  3. 3Build the estate — the TR 38.901 maths, plotted
  4. 4Calibration — differential evolution, the gate
  5. 5Inference — tilt sweep, a cell asleep
  6. 6Recap
To run it

Three commands, one virtualenv

The notebook imports the twin's own package, so it runs from a clone of the telecogecoTwin repository. The two CSVs above are the example estate it loads in stage 2 — a fictional hex layout with generic field names (cell_id, cell_el_deg, …), no operator data.

git clone https://github.com/telecogeco/telecogecoTwin
pip install -r requirements.txt -r notebooks/requirements-notebook.txt
jupyter lab notebooks/telecogecoTwin_walkthrough.ipynb
Runs entirely on the generic rung — simulation, generic 3GPP defaults (uncalibrated). Nothing in the notebook or its data comes from, or makes a claim about, any real network.

Prefer the HTTP service? The explainer's “The flow” section drives the same stages through the FastAPI endpoints.